Qwen: Qwen3 VL 235B A22B Instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Everything else
| Max output | 33K |
|---|---|
| Input / 1M | $0.21 |
| Output / 1M | $1.90 |
| Cache read / 1M | $0.1 |
| Cache write / 1M | — |
| 1M in + 1M out | $2.11 |
| Takes | text, image |
| Returns | text |
| Tools | yes |
| Reasoning | no |
| Open weights | yes |
| Released | 2025-09-23 |
| Knowledge cutoff | 2025-03-31 |
| Retires | — |
| Catalog id | qwen/qwen3-vl-235b-a22b-instruct |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.